Atomistic Line Graph Neural Network for improved materials property predictions

By Kamal Choudhary, Brian L. DeCost. npj Computational Materials, 2021

757 citations recorded by the source corpus.

Graph neural networks (GNN) have been shown to provide substantial performance improvements for atomistic material representation and modeling compared with descriptor-based machine learning models. While most existing GNN models for atomistic predictions are based on atomic distance information, they do not explicitly incorporate bond angles, which are critical for distinguishing many atomic structures. Furthermore, many material properties are known to be sensitive to slight changes in bond angles. We present an Atomistic Line Graph Neural Network (ALIGNN), a GNN architecture that performs message passing on both the interatomic bond graph and its line graph corresponding to bond angles. We demonstrate that angle information can be explicitly and efficiently included, leading to improved performance on multiple atomistic prediction tasks. We ALIGNN models for predicting 52 solid-state and molecular properties available in the JARVIS-DFT, Materials project, and QM9 databases. ALIGNN can outperform some previously reported GNN models on atomistic prediction tasks by up to 85% in accuracy with better or comparable model training speed.

Subfields: Computational Theory and Mathematics, Materials Chemistry

View Paper: https://www.semanticscholar.org/paper/28b5dfe6035013e9345ec4a3eef5f0c5307a3fcb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Materials Chemistry

Citations in the corpus

A universal graph deep learning interatomic potential for the periodic table (2022, background): “Traditional graph neural network models for materials 24–27 have proven to be exceptionally effective for general materials property predictions 24–27 , but are not suitable as IAPs due to the lack of physical constraints such as a continuity of energies and forces with the changes to the length…”
Recent advances and applications of deep learning methods in materials science (2021, methodology): “Models such as SchNet, crystal graph convolutional neural network (CGCNN), improved crystal graph convolutional neural network (iCGCNN), directional message passing neural network (DimeNet), atomistic line graph neural network (ALIGNN) and materials graph neural network (MEGNet) shown in Table 1 hav”